JP2024159685A - Electronics - Google Patents

Abstract

To provide an electronic apparatus that can use an agent system that makes an interaction with a user with the understanding of the emotions of the user and an agent.SOLUTION: A to-do management application using an electronic apparatus can use an agent system including an emotion determination unit that determines the emotions of a user or the emotions of an agent, and an interaction processing unit that determines the details of the utterance of the agent for making an interaction with the user on the basis of the emotions determined by the emotion determination unit, in place of a user 10 (parent) who is not at home, a robot 100 having the agent system mounted therein determines whether a behavior history target (child 400) who stays at home has done their homework, makes an inquiry to a sentence creation model 55 about a situation where the child has done their homework (positive) and a situation where the child has not done their homework (negative), and thereby can receive advice (appropriate words) and say the appropriate words to the child 400 by voice.SELECTED DRAWING: Figure 13

Description

The present invention relates to electronic devices.

Patent Document 1 discloses a technology for determining an appropriate robot behavior in response to a user's state. The conventional technology in Patent Document 1 recognizes the user's reaction when the robot performs a specific action, and if the robot is unable to determine an action to be taken in response to the recognized user reaction, it updates the robot's behavior by receiving information about an action appropriate to the recognized user's state from a server.

Patent No. 6053847

The present invention aims to provide an electronic device that can utilize an agent system that understands the emotions of the user and the device itself and can converse with the user.

According to a first aspect of the present invention, an electronic device is provided. The electronic device is an electronic device that can use an agent system including an emotion determination unit that determines the emotion of a user or an emotion of an agent, and a dialogue processing unit that determines the content of the agent's speech to dialogue with the user based on the emotion determined by the emotion determination unit, and is characterized in that the electronic device is equipped with an acquisition unit that can acquire information about the user's state, a judgment unit that judges whether a specific behavior of a behavior history target is achieved or not based on the behavior history of the behavior history target, an execution unit that causes the agent system to generate a sentence regarding the specific behavior based on the judgment result of the judgment unit regarding the specific behavior when the user issues an instruction to judge whether the specific behavior is achieved or not, and an output unit that outputs the sentence generated in the agent system to the user as the content of the speech.

The present invention is characterized in that it further includes a storage unit that stores action history images captured in chronological order following the action of the action history target, and the determination unit determines whether the specific action has been achieved or not based on the action history images stored in the storage unit.

The present invention is characterized in that a relationship is established between the user and the behavior history target, in which the user is the manager or guardian and the behavior history target is the managed or protected.

The present invention is characterized in that the relationship between the user and the behavior history target is that between a parent and a child under the parent's care, and the specific behavior is selected from behaviors that have been registered in advance as a to-do list for the child.

1 illustrates a schematic diagram of an example of a system 5 according to the present embodiment. 2 shows a schematic functional configuration of the robot 100. 10 shows an example of an operation flow of the robot 100. 1 illustrates an example of a hardware configuration of a computer 1200. 1 shows an emotion map onto which multiple emotions are mapped. 9 shows an emotion map 900 onto which multiple emotions are mapped. 2 shows an outline of the functional configuration of the agent system. An example of the operation of the agent system is shown. An example of the operation of the agent system is shown. 1 illustrates an example of a hardware configuration of smart glasses. 1 shows an example of how an agent system using smart glasses is used. 2 illustrates an example of a hardware configuration of a smart pendant. This is a front view of a group of images taken in time series by a camera managed and controlled by the agent system for use in determining the behavior history of a behavior history target specified by a user. 11 is a control flowchart showing a flow of acquiring an action history in the processing of a to-do management application executed by a control device of a robot. 15 is a control flowchart showing the flow of an interrupt routine that is executed when a request for determining an action history is made during the action history acquisition in FIG. 14 .

The present invention will be described below through embodiments of the invention, but the following embodiments do not limit the invention according to the claims. Furthermore, not all of the combinations of features described in the embodiments are necessarily essential to the solution of the invention.

1 is a schematic diagram of an example of a system 5 according to the present embodiment. The system 5 includes a robot 100, a robot 101, a robot 102, and a server 300. A user 10a, a user 10b, a user 10c, and a user 10d are users of the robot 100. A user 11a, a user 11b, and a user 11c are users of the robot 101. A user 12a and a user 12b are users of the robot 102. In the description of the present embodiment, the user 10a, the user 10b, the user 10c, and the user 10d may be collectively referred to as the user 10. The user 11a, the user 11b, and the user 11c may be collectively referred to as the user 11. The user 12a and the user 12b may be collectively referred to as the user 12. The robot 101 and the robot 102 have substantially the same functions as the robot 100. Therefore, the system 5 will be described by mainly focusing on the functions of the robot 100.

The robot 100 converses with the user 10 and provides images to the user 10. At this time, the robot 100 cooperates with a server 300 or the like with which it can communicate via the communication network 20 to converse with the user 10 and provide images, etc. to the user 10. For example, the robot 100 not only learns appropriate conversation by itself, but also cooperates with the server 300 to learn how to have a more appropriate conversation with the user 10. The robot 100 also records captured image data of the user 10 in the server 300, and requests the image data, etc. from the server 300 as necessary to provide it to the user 10.

The robot 100 also has an emotion value that represents the type of its own emotion. For example, the robot 100 has emotion values that represent the strength of each of the emotions of "happiness," "anger," "sorrow," "pleasure," "discomfort," "relief," "anxiety," "sorrow," "excitement," "worry," "relief," "fulfillment," "emptiness," and "neutral." When the robot 100 converses with the user 10 when its excitement emotion value is high, for example, it speaks at a fast speed. In this way, the robot 100 can express its own emotions through its actions.

The robot 100 may be configured to determine an action of the robot 100 corresponding to the emotion of the user 10 by matching the sentence generation model with the emotion engine. Specifically, the robot 100 may be configured to recognize the action of the user 10, determine the emotion of the user 10 regarding the action of the user, and determine an action of the robot 100 corresponding to the determined emotion.

More specifically, when the robot 100 recognizes the behavior of the user 10, the robot 100 automatically generates the behavioral content that the robot 100 should take in response to the behavior of the user 10, using a preset sentence generation model. The sentence generation model may be interpreted as an algorithm and calculation for automatic dialogue processing by text. The sentence generation model is publicly known as disclosed in, for example, JP 2018-081444 A and chatGPT (Internet search <URL: https://openai.com/blog/chatgpt>), and therefore a detailed description thereof will be omitted. Such a sentence generation model is configured by a large language model (LLM: Large Language Model).

As described above, this embodiment combines a large-scale language model with an emotion engine, thereby making it possible to reflect the emotions of the user 10 and the robot 100, as well as various linguistic information, in the behavior of the robot 100. In other words, according to this embodiment, a synergistic effect can be obtained by combining a sentence generation model with an emotion engine.

The robot 100 also has a function of recognizing the behavior of the user 10. The robot 100 recognizes the behavior of the user 10 by analyzing the facial image of the user 10 acquired by the camera function and the voice of the user 10 acquired by the microphone function. The robot 100 determines the behavior to be performed by the robot 100 based on the recognized behavior of the user 10, etc.

The robot 100 stores rules that define the actions that the robot 100 will take based on the emotions of the user 10, the emotions of the robot 100, and the actions of the user 10, and performs various actions according to the rules.

Specifically, the robot 100 has reaction rules for determining the behavior of the robot 100 based on the emotions of the user 10, the emotions of the robot 100, and the behavior of the user 10. For example, the reaction rules define the behavior of the robot 100 as "laughing" when the behavior of the user 10 is "laughing". The reaction rules also define the behavior of the robot 100 as "apologizing" when the behavior of the user 10 is "angry". The reaction rules also define the behavior of the robot 100 as "answering" when the behavior of the user 10 is "asking a question". The reaction rules also define the behavior of the robot 100 as "calling out" when the behavior of the user 10 is "sad".

When the robot 100 recognizes that the behavior of the user 10 is "angry" based on the reaction rules, the robot 100 selects the behavior of "apologizing" defined in the reaction rules as the behavior to be executed by the robot 100. For example, when the robot 100 selects the behavior of "apologizing", the robot 100 performs the motion of "apologizing" and outputs a voice expressing the words "apologize".

In addition, when the emotion of the robot 100 is "normal" (i.e., "happy" = 0, "anger" = 0, "sad" = 0, "happy" = 0) and the condition that the state of the user 10 is "alone and looks lonely" is satisfied, it is defined that the emotion of the robot 100 will change to "worried" and that the robot 100 will be able to execute the action of "calling out."

When the robot 100 recognizes based on the reaction rules that the current emotion of the robot 100 is "normal" and that the user 10 is alone and seems lonely, the robot 100 increases the emotion value of "sadness" of the robot 100. In addition, the robot 100 selects the action of "calling out" defined in the reaction rules as the action to be performed toward the user 10. For example, when the robot 100 selects the action of "calling out", it converts the words "What's wrong?", which express concern, into a worried voice and outputs it.

The robot 100 also transmits to the server 300 user reaction information indicating that this action has elicited a positive reaction from the user 10. The user reaction information includes, for example, the user action of "getting angry," the robot 100 action of "apologizing," the fact that the user 10's reaction was positive, and the attributes of the user 10.

The server 300 stores the user reaction information received from the robot 100. The server 300 receives and stores user reaction information not only from the robot 100, but also from each of the robots 101 and 102. The server 300 then analyzes the user reaction information from the robots 100, 101, and 102, and updates the reaction rules.

The robot 100 receives the updated reaction rules from the server 300 by inquiring about the updated reaction rules from the server 300. The robot 100 incorporates the updated reaction rules into the reaction rules stored in the robot 100. This allows the robot 100 to incorporate the reaction rules acquired by the robot 101, the robot 102, etc. into its own reaction rules.

Figure 2 shows a schematic functional configuration of the robot 100. The robot 100 has a sensor unit 200, a sensor module unit 210, a storage unit 220, a user state recognition unit 230, an emotion determination unit 232, a behavior recognition unit 234, a behavior determination unit 236, a memory control unit 238, a behavior control unit 250, a control target 252, and a communication processing unit 280.

The controlled object 252 includes a display device, a speaker, LEDs in the eyes, and motors for driving the arms, hands, legs, etc. The posture and gestures of the robot 100 are controlled by controlling the motors of the arms, hands, legs, etc. Some of the emotions of the robot 100 can be expressed by controlling these motors. In addition, the facial expressions of the robot 100 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 100. The posture, gestures, and facial expressions of the robot 100 are examples of the attitude of the robot 100.

The sensor unit 200 includes a microphone 201, a 3D depth sensor 202, a 2D camera 203, and a distance sensor 204. The microphone 201 continuously detects sound and outputs sound data. The microphone 201 may be provided on the head of the robot 100 and may have a function of performing binaural recording. The 3D depth sensor 202 detects the contour of an object by continuously irradiating an infrared pattern and analyzing the infrared pattern from infrared images continuously captured by the infrared camera. The 2D camera 203 is an example of an image sensor. The 2D camera 203 captures images using visible light and generates visible light video information. The distance sensor 204 detects the distance to an object by irradiating, for example, a laser or ultrasonic waves. The sensor unit 200 may also include a clock, a gyro sensor, a touch sensor, a sensor for motor feedback, and the like.

Note that, among the components of the robot 100 shown in FIG. 2, the components other than the control target 252 and the sensor unit 200 are examples of components of the behavior control system of the robot 100. The behavior control system of the robot 100 controls the control target 252.

The storage unit 220 includes reaction rules 221 and history data 222. The history data 222 includes the user 10's past emotional values and behavioral history. The emotional values and behavioral history are recorded for each user 10, for example, by being associated with the user 10's identification information. At least a part of the storage unit 220 is implemented by a storage medium such as a memory. It may include a person DB that stores the face image of the user 10, the attribute information of the user 10, and the like. Note that the functions of the components of the robot 100 shown in FIG. 2, excluding the control target 252, the sensor unit 200, and the storage unit 220, can be realized by the CPU operating based on a program. For example, the functions of these components can be implemented as the operation of the CPU by the operating system (OS) and a program that operates on the OS.

The sensor module unit 210 includes a voice emotion recognition unit 211, a speech understanding unit 212, a facial expression recognition unit 213, and a face recognition unit 214. Information detected by the sensor unit 200 is input to the sensor module unit 210. The sensor module unit 210 analyzes the information detected by the sensor unit 200 and outputs the analysis result to the user state recognition unit 230.

The voice emotion recognition unit 211 of the sensor module unit 210 analyzes the voice of the user 10 detected by the microphone 201 to recognize the emotion of the user 10. For example, the voice emotion recognition unit 211 extracts features such as frequency components of the voice, and recognizes the emotion of the user 10 based on the extracted features. The speech understanding unit 212 analyzes the voice of the user 10 detected by the microphone 201, and outputs text information representing the content of the user 10's utterance.

The facial expression recognition unit 213 recognizes the facial expression and emotions of the user 10 from the image of the user 10 captured by the 2D camera 203. For example, the facial expression recognition unit 213 recognizes the facial expression and emotions of the user 10 based on the shape, positional relationship, etc. of the eyes and mouth.

The face recognition unit 214 recognizes the face of the user 10. The face recognition unit 214 recognizes the user 10 by matching a face image stored in a person DB (not shown) with a face image of the user 10 captured by the 2D camera 203.

The user state recognition unit 230 recognizes the state of the user 10 based on the information analyzed by the sensor module unit 210. For example, it mainly performs processing related to perception using the analysis results of the sensor module unit 210. For example, it generates perceptual information such as "Daddy is alone" or "There is a 90% chance that Daddy is not smiling." It then performs processing to understand the meaning of the generated perceptual information. For example, it generates semantic information such as "Daddy is alone and looks lonely."

The emotion determination unit 232 determines an emotion value indicating the emotion of the user 10 based on the information analyzed by the sensor module unit 210 and the state of the user 10 recognized by the user state recognition unit 230. For example, the information analyzed by the sensor module unit 210 and the recognized state of the user 10 are input to a pre-trained neural network to obtain an emotion value indicating the emotion of the user 10.

Here, the emotion value indicating the emotion of user 10 is a value indicating the positive or negative emotion of the user. For example, if the user's emotion is a cheerful emotion accompanied by a sense of pleasure or comfort, such as "joy," "pleasure," "comfort," "relief," "excitement," "relief," and "fulfillment," the value is positive, and the more cheerful the emotion, the larger the value. If the user's emotion is an unpleasant emotion, such as "anger," "sorrow," "discomfort," "anxiety," "sorrow," "worry," and "emptiness," the value is negative, and the more unpleasant the emotion, the larger the absolute value of the negative value. If the user's emotion is none of the above ("normal"), the value is 0.

In addition, the emotion determination unit 232 determines an emotion value indicating the emotion of the robot 100 based on the information analyzed by the sensor module unit 210 and the state of the user 10 recognized by the user state recognition unit 230 .
The emotion value of the robot 100 includes emotion values for each of a plurality of emotion categories, and is, for example, a value (0 to 5) indicating the strength of each of "happiness,""anger,""sorrow," and "happiness."

Specifically, the emotion determination unit 232 determines an emotion value indicating the emotion of the robot 100 according to rules for updating the emotion value of the robot 100 that are determined in association with the information analyzed by the sensor module unit 210 and the state of the user 10 recognized by the user state recognition unit 230.

For example, if the user state recognition unit 230 recognizes that the user 10 looks lonely, the emotion determination unit 232 increases the emotion value of "sadness" of the robot 100. Also, if the user state recognition unit 230 recognizes that the user 10 is smiling, the emotion determination unit 232 increases the emotion value of "happy" of the robot 100.

The emotion determination unit 232 may determine the emotion value indicating the emotion of the robot 100 by further considering the state of the robot 100. For example, when the battery level of the robot 100 is low or when the surrounding environment of the robot 100 is completely dark, the emotion value of "sadness" of the robot 100 may be increased. Furthermore, when the user 10 continues to talk to the robot 100 despite the battery level being low, the emotion value of "anger" may be increased.

The behavior recognition unit 234 recognizes the behavior of the user 10 based on the information analyzed by the sensor module unit 210 and the state of the user 10 recognized by the user state recognition unit 230. For example, the information analyzed by the sensor module unit 210 and the recognized state of the user 10 are input to a pre-trained neural network, the probability of each of a number of predetermined behavioral categories (e.g., "laughing," "anger," "asking a question," "sad") is obtained, and the behavioral category with the highest probability is recognized as the behavior of the user 10.

As described above, in this embodiment, the robot 100 identifies the user 10 and acquires the contents of the user's utterance. When acquiring and using the contents of the utterance, the robot 100 obtains the necessary consent in accordance with laws and regulations from the user 10, and the behavior control system of the robot 100 according to this embodiment takes into consideration the protection of the personal information and privacy of the user 10.

The behavior determination unit 236 determines an action corresponding to the behavior of the user 10 recognized by the behavior recognition unit 234 based on the current emotion value of the user 10 determined by the emotion determination unit 232, the history data 222 of past emotion values determined by the emotion determination unit 232 before the current emotion value of the user 10 was determined, and the emotion value of the robot 100. In this embodiment, the behavior determination unit 236 uses one most recent emotion value included in the history data 222 as the past emotion value of the user 10, but the disclosed technology is not limited to this aspect. For example, the behavior determination unit 236 may use the most recent multiple emotion values as the past emotion value of the user 10, or may use an emotion value from a unit period ago, such as one day ago. In addition, the behavior determination unit 236 may determine an action corresponding to the behavior of the user 10 by further considering not only the current emotion value of the robot 100 but also the history of the past emotion values of the robot 100. The behavior determined by the behavior determination unit 236 includes gestures performed by the robot 100 or the contents of speech uttered by the robot 100.

The behavior decision unit 236 according to this embodiment decides the behavior of the robot 100 as the behavior corresponding to the behavior of the user 10, based on a combination of the past and current emotion values of the user 10, the emotion value of the robot 100, the behavior of the user 10, and the reaction rules 221. For example, when the past emotion value of the user 10 is a positive value and the current emotion value is a negative value, the behavior decision unit 236 decides the behavior for changing the emotion value of the user 10 to a positive value as the behavior corresponding to the behavior of the user 10.

The reaction rules 221 define the behavior of the robot 100 according to a combination of the past and current emotion values of the user 10, the emotion value of the robot 100, and the behavior of the user 10. For example, when the past emotion value of the user 10 is a positive value and the current emotion value is a negative value, and the behavior of the user 10 is sad, a combination of gestures and speech content when asking a question to encourage the user 10 with gestures is defined as the behavior of the robot 100.

For example, the reaction rule 221 defines behaviors of the robot 100 for patterns of the emotion values of the robot 100 (1296 patterns, which are the fourth power of six values of "joy", "anger", "sorrow", and "pleasure", from "0" to "5"), combination patterns of the past emotion values and the current emotion values of the user 10, and all combinations of the behavior patterns of the user 10. That is, for each pattern of the emotion values of the robot 100, behaviors of the robot 100 are defined according to the behavior patterns of the user 10 for each of a plurality of combinations of the past emotion values and the current emotion values of the user 10, such as negative values and negative values, negative values and positive values, positive values and negative values, positive values and positive values, negative values and normal values, and normal values and normal values. Note that, when the user 10 makes an utterance intending to continue a conversation from a past topic, such as "I want to talk about that topic we talked about last time", the behavior determining unit 236 may transition to an operation mode in which the behavior of the robot 100 is determined using the history data 222.
The reaction rules 221 may prescribe at least one of a gesture and a statement as the behavior of the robot 100 for each of the patterns (1296 patterns) of the emotion value of the robot 100. Alternatively, the reaction rules 221 may prescribe at least one of a gesture and a statement as the behavior of the robot 100 for each group of patterns of the emotion value of the robot 100.

For each gesture included in the behavior of the robot 100 defined in the reaction rules 221, the strength of the gesture is predefined. For each utterance content included in the behavior of the robot 100 defined in the reaction rules 221, the strength of the utterance content is predefined.

The memory control unit 238 determines whether or not to store data including the behavior of the user 10 in the history data 222 based on the predetermined behavior strength for the behavior determined by the behavior determination unit 236 and the emotion value of the robot 100 determined by the emotion determination unit 232.
Specifically, when a total intensity value, which is the sum of the sum of the emotion values for each of the multiple emotion classifications of the robot 100, the predetermined intensity for the gestures included in the behavior determined by the behavior determination unit 236, and the predetermined intensity for the speech content included in the behavior determined by the behavior determination unit 236, is equal to or greater than a threshold value, it is decided to store data including the behavior of the user 10 in the history data 222.

When the memory control unit 238 decides to store data including the behavior of the user 10 in the history data 222, it stores in the history data 222 the behavior determined by the behavior determination unit 236, information analyzed by the sensor module unit 210 from the present time up to a certain period of time ago (e.g., all surrounding information such as data on the sound, images, smells, etc. of the scene), and the state of the user 10 recognized by the user state recognition unit 230 (e.g., the facial expression, emotions, etc. of the user 10).

The behavior control unit 250 controls the control target 252 based on the behavior determined by the behavior determination unit 236. For example, when the behavior determination unit 236 determines an behavior including speaking, the behavior control unit 250 outputs a sound from a speaker included in the control target 252. At this time, the behavior control unit 250 may determine the speaking speed of the sound based on the emotion value of the robot 100. For example, the behavior control unit 250 determines a faster speaking speed as the emotion value of the robot 100 increases. In this way, the behavior control unit 250 determines the execution form of the behavior determined by the behavior determination unit 236 based on the emotion value determined by the emotion determination unit 232.

The behavior control unit 250 may recognize a change in the user 10's emotions in response to the execution of the behavior determined by the behavior determination unit 236. For example, the change in emotions may be recognized based on the voice or facial expression of the user 10. Alternatively, the change in emotions may be recognized based on the detection of an impact by a touch sensor included in the sensor unit 200. If an impact is detected by the touch sensor included in the sensor unit 200, the user 10's emotions may be recognized as having worsened, and if the detection result of the touch sensor included in the sensor unit 200 indicates that the user 10 is smiling or happy, the user 10's emotions may be recognized as having improved. Information indicating the user 10's reaction is output to the communication processing unit 280.

In addition, after the behavior control unit 250 executes the behavior determined by the behavior determination unit 236 in the execution form determined according to the emotion of the robot 100, the emotion determination unit 232 further changes the emotion value of the robot 100 based on the user's reaction to the execution of the behavior. Specifically, the emotion determination unit 232 increases the emotion value of "happiness" of the robot 100 when the user's reaction to the behavior determined by the behavior determination unit 236 being performed on the user in the execution form determined by the behavior control unit 250 is not bad. In addition, the emotion determination unit 232 increases the emotion value of "sadness" of the robot 100 when the user's reaction to the behavior determined by the behavior determination unit 236 being performed on the user in the execution form determined by the behavior control unit 250 is bad.

Furthermore, the behavior control unit 250 expresses the emotion of the robot 100 based on the determined emotion value of the robot 100. For example, when the behavior control unit 250 increases the emotion value of "happiness" of the robot 100, it controls the control object 252 to make the robot 100 perform a happy gesture. When the behavior control unit 250 increases the emotion value of "sadness" of the robot 100, it controls the control object 252 to make the robot 100 assume a droopy posture.

The communication processing unit 280 is responsible for communication with the server 300. As described above, the communication processing unit 280 transmits user reaction information to the server 300. In addition, the communication processing unit 280 receives updated reaction rules from the server 300. When the communication processing unit 280 receives updated reaction rules from the server 300, it updates the reaction rules 221.

The server 300 communicates between the robots 100, 101, and 102 and the server 300, receives user reaction information sent from the robot 100, and updates the reaction rules based on reaction rules that include actions that have received positive reactions.

Figure 3 shows an example of an outline of an operation flow relating to the operation of determining an action in the robot 100. The operation flow shown in Figure 3 is executed repeatedly. At this time, it is assumed that information analyzed by the sensor module unit 210 is input. Note that "S" in the operation flow indicates the step that is executed.

First, in step S100, the user state recognition unit 230 recognizes the state of the user 10 based on the information analyzed by the sensor module unit 210.

In step S102, the emotion determination unit 232 determines an emotion value indicating the emotion of the user 10 based on the information analyzed by the sensor module unit 210 and the state of the user 10 recognized by the user state recognition unit 230.

In step S103, the emotion determination unit 232 determines an emotion value indicating the emotion of the robot 100 based on the information analyzed by the sensor module unit 210 and the state of the user 10 recognized by the user state recognition unit 230. The emotion determination unit 232 adds the determined emotion value of the user 10 to the history data 222.

In step S104, the behavior recognition unit 234 recognizes the behavior classification of the user 10 based on the information analyzed by the sensor module unit 210 and the state of the user 10 recognized by the user state recognition unit 230.

In step S106, the behavior decision unit 236 decides the behavior of the robot 100 based on a combination of the current emotion value of the user 10 determined in step S102 and the past emotion values included in the history data 222, the emotion value of the robot 100, the behavior of the user 10 recognized by the behavior recognition unit 234, and the reaction rules 221.

In step S108, the behavior control unit 250 controls the control object 252 based on the behavior determined by the behavior determination unit 236.

In step S110, the memory control unit 238 calculates a total intensity value based on the predetermined action intensity for the action determined by the action determination unit 236 and the emotion value of the robot 100 determined by the emotion determination unit 232.

In step S112, the storage control unit 238 determines whether the total intensity value is equal to or greater than the threshold value. If the total intensity value is less than the threshold value, the process ends without storing data including the behavior of the user 10 in the history data 222. On the other hand, if the total intensity value is equal to or greater than the threshold value, the process proceeds to step S114.

In step S114, the behavior determined by the behavior determination unit 236, the information analyzed by the sensor module unit 210 from the present time up to a certain period of time ago, and the state of the user 10 recognized by the user state recognition unit 230 are stored in the history data 222.

As described above, according to the robot 100, an emotion value indicating the emotion of the robot 100 is determined based on the user state, and whether or not to store data including the behavior of the user 10 in the history data 222 is determined based on the emotion value of the robot 100. This makes it possible to reduce the capacity of the history data 222 that stores data including the behavior of the user 10. For example, when the robot 100 determines that the user state 10 years from now is the same as that 10 years ago, the robot 100 can present to the user 10 all kinds of peripheral information, such as the state of the user 10 10 years ago (e.g., the facial expression, emotions, etc. of the user 10), and data on the sound, image, smell, etc. of the location.

According to the robot 100, the robot 100 can be made to perform an appropriate action in response to the action of the user 10. Conventionally, the user's actions were classified and the action including the robot's facial expression and appearance was determined. In contrast, the robot 100 determines the current emotional value of the user 10 and performs an action on the user 10 based on the past emotional value and the current emotional value. Therefore, for example, if the user 10 who was cheerful yesterday is depressed today, the robot 100 can make an utterance such as "You were cheerful yesterday, but what's wrong with you today?" The robot 100 can also make an utterance with gestures. For example, if the user 10 who was depressed yesterday is cheerful today, the robot 100 can make an utterance such as "You were depressed yesterday, but you look cheerful today, don't you?" For example, if the user 10 who was cheerful yesterday is more cheerful today than yesterday, the robot 100 can make an utterance such as "You're more cheerful today than yesterday. Has something better happened than yesterday?" Furthermore, for example, the robot 100 can say to a user 10 whose emotion value is equal to or greater than 0 and whose emotion value fluctuation range continues to be within a certain range, "You've been feeling stable lately, which is good."

For example, the robot 100 can ask the user 10, "Did you finish the homework I told you about yesterday?", and if the user 10 responds, "I did it," it can utter a positive utterance such as "Great!" and make a positive gesture such as clapping or a thumbs up. For example, when the user 10 utters, "The presentation you gave the day before yesterday went well," the robot 100 can utter a positive utterance such as "You did a great job!" and make the above-mentioned positive gesture. In this way, the robot 100 can be expected to make the user 10 feel a sense of closeness to the robot 100 by performing actions based on the state history of the user 10.

In the above embodiment, the robot 100 recognizes the user 10 using a facial image of the user 10, but the disclosed technology is not limited to this aspect. For example, the robot 100 may recognize the user 10 using a voice emitted by the user 10, an email address of the user 10, an SNS ID of the user 10, or an ID card with a built-in wireless IC tag that the user 10 possesses.

The robot 100 is an example of an electronic device equipped with a behavior control system. The application of the behavior control system is not limited to the robot 100, and the behavior control system can be applied to various electronic devices. Furthermore, the functions of the server 300 may be implemented by one or more computers. At least some of the functions of the server 300 may be implemented by a virtual machine. Furthermore, at least some of the functions of the server 300 may be implemented in the cloud.

Figure 4 shows an example of a hardware configuration of a computer 1200 functioning as the robot 100 and the server 300. A program installed on the computer 1200 can cause the computer 1200 to function as one or more "parts" of an apparatus according to the present embodiment, or to execute operations or one or more "parts" associated with an apparatus according to the present embodiment, and/or to execute a process or steps of the process according to the present embodiment. Such a program can be executed by the CPU 1212 to cause the computer 1200 to execute specific operations associated with some or all of the blocks of the flowcharts and block diagrams described herein.

The computer 1200 according to this embodiment includes a CPU 1212, a RAM 1214, and a graphics controller 1216, which are connected to each other by a host controller 1210. The computer 1200 also includes input/output units such as a communication interface 1222, a storage device 1224, a DVD drive 1226, and an IC card drive, which are connected to the host controller 1210 via an input/output controller 1220. The DVD drive 1226 may be a DVD-ROM drive, a DVD-RAM drive, or the like. The storage device 1224 may be a hard disk drive, a solid state drive, or the like. The computer 1200 also includes a ROM 1230 and a legacy input/output unit such as a keyboard, which are connected to the input/output controller 1220 via an input/output chip 1240.

The CPU 1212 operates according to the programs stored in the ROM 1230 and the RAM 1214, thereby controlling each unit. The graphics controller 1216 acquires image data generated by the CPU 1212 into a frame buffer or the like provided in the RAM 1214 or into itself, and causes the image data to be displayed on the display device 1218.

The communication interface 1222 communicates with other electronic devices via a network. The storage device 1224 stores programs and data used by the CPU 1212 in the computer 1200. The DVD drive 1226 reads programs or data from a DVD-ROM 1227 or the like and provides them to the storage device 1224. The IC card drive reads programs and data from an IC card and/or writes programs and data to an IC card.

ROM 1230 stores therein a boot program or the like executed by computer 1200 upon activation, and/or a program that depends on the hardware of computer 1200. I/O chip 1240 may also connect various I/O units to I/O controller 1220 via USB ports, parallel ports, serial ports, keyboard ports, mouse ports, etc.

The programs are provided by a computer-readable storage medium such as a DVD-ROM 1227 or an IC card. The programs are read from the computer-readable storage medium, installed in the storage device 1224, RAM 1214, or ROM 1230, which are also examples of computer-readable storage media, and executed by the CPU 1212. The information processing described in these programs is read by the computer 1200, and brings about cooperation between the programs and the various types of hardware resources described above. An apparatus or method may be constructed by realizing the operation or processing of information according to the use of the computer 1200.

For example, when communication is performed between computer 1200 and an external device, CPU 1212 may execute a communication program loaded into RAM 1214 and instruct communication interface 1222 to perform communication processing based on the processing described in the communication program. Under the control of CPU 1212, communication interface 1222 reads transmission data stored in a transmission buffer area provided in RAM 1214, storage device 1224, DVD-ROM 1227, or a recording medium such as an IC card, and transmits the read transmission data to the network, or writes received data received from the network to a reception buffer area or the like provided on the recording medium.

The CPU 1212 may also cause all or a necessary portion of a file or database stored in an external recording medium such as the storage device 1224, DVD drive 1226 (DVD-ROM 1227), IC card, etc. to be read into the RAM 1214, and perform various types of processing on the data on the RAM 1214. The CPU 1212 may then write back the processed data to the external recording medium.

Various types of information, such as various types of programs, data, tables, and databases, may be stored in the recording medium and may undergo information processing. The CPU 1212 may perform various types of processing on the data read from the RAM 1214, including various types of operations, information processing, conditional judgment, conditional branching, unconditional branching, information search/replacement, etc., as described throughout this disclosure and specified by the instruction sequence of the program, and writes back the results to the RAM 1214. The CPU 1212 may also search for information in a file, database, etc. in the recording medium. For example, when multiple entries each having an attribute value of a first attribute associated with an attribute value of a second attribute are stored in the recording medium, the CPU 1212 may search for an entry whose attribute value of the first attribute matches a specified condition from among the multiple entries, read the attribute value of the second attribute stored in the entry, and thereby obtain the attribute value of the second attribute associated with the first attribute that satisfies a predetermined condition.

The above-described programs or software modules may be stored in a computer-readable storage medium on or near the computer 1200. In addition, a recording medium such as a hard disk or RAM provided in a server system connected to a dedicated communication network or the Internet can be used as a computer-readable storage medium, thereby providing the programs to the computer 1200 via the network.

The blocks in the flowcharts and block diagrams in this embodiment may represent stages of a process in which an operation is performed or "parts" of a device responsible for performing the operation. Particular stages and "parts" may be implemented by dedicated circuitry, programmable circuitry provided with computer-readable instructions stored on a computer-readable storage medium, and/or a processor provided with computer-readable instructions stored on a computer-readable storage medium. The dedicated circuitry may include digital and/or analog hardware circuits and may include integrated circuits (ICs) and/or discrete circuits. The programmable circuitry may include reconfigurable hardware circuits including AND, OR, XOR, NAND, NOR, and other logical operations, flip-flops, registers, and memory elements, such as, for example, field programmable gate arrays (FPGAs) and programmable logic arrays (PLAs).

A computer-readable storage medium may include any tangible device capable of storing instructions that are executed by a suitable device, such that a computer-readable storage medium having instructions stored thereon comprises an article of manufacture that includes instructions that can be executed to create means for performing the operations specified in the flowchart or block diagram. Examples of computer-readable storage media may include electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, and the like. More specific examples of computer-readable storage media may include floppy disks, diskettes, hard disks, random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs or flash memories), electrically erasable programmable read-only memories (EEPROMs), static random access memories (SRAMs), compact disk read-only memories (CD-ROMs), digital versatile disks (DVDs), Blu-ray disks, memory sticks, integrated circuit cards, and the like.

The computer readable instructions may include either assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including object-oriented programming languages such as Smalltalk, JAVA, C++, etc., and conventional procedural programming languages such as the "C" programming language or similar programming languages.

The computer-readable instructions may be provided to a processor of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, or a programmable circuit, either locally or over a local area network (LAN), a wide area network (WAN), such as the Internet, so that the processor of the general-purpose computer, special-purpose computer, or other programmable data processing apparatus, or the programmable circuit, executes the computer-readable instructions to generate means for performing the operations specified in the flowcharts or block diagrams. Examples of processors include computer processors, processing units, microprocessors, digital signal processors, controllers, microcontrollers, etc.

The present invention has been described above using an embodiment, but the technical scope of the present invention is not limited to the scope described in the above embodiment. It is clear to those skilled in the art that various modifications and improvements can be made to the above embodiment. It is clear from the claims that forms with such modifications or improvements can also be included in the technical scope of the present invention.

The order of execution of each process, such as operations, procedures, steps, and stages, in the devices, systems, programs, and methods shown in the claims, specifications, and drawings is not specifically stated as "before" or "prior to," and it should be noted that the processes may be performed in any order, unless the output of a previous process is used in a later process. Even if the operational flow in the claims, specifications, and drawings is explained using "first," "next," etc. for convenience, it does not mean that it is necessary to perform the processes in that order.

The emotion determination unit 232 may determine the user's emotion according to a specific mapping. Specifically, the emotion determination unit 232 may determine the user's emotion according to an emotion map (see FIG. 5), which is a specific mapping.

5 is a diagram showing an emotion map 300 on which multiple emotions are mapped. In the emotion map 300, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. Emotions that represent states and actions arising from mental states are arranged on the outer sides of the concentric circles. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 300, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

(1) For example, if the emotion engine, which is the emotion determination unit 232 of the robot 100, detects emotions at approximately 100 msec, the frequency of the determination of the reaction action of the robot 100 (e.g., a backchannel) may be set to at least the same timing as the detection frequency of the emotion engine (100 msec), or may be set to an earlier timing. The detection frequency of the emotion engine may be interpreted as the sampling rate.

By detecting emotions in about 100 msec and immediately performing a corresponding reaction (e.g., a backchannel), unnatural backchannels can be avoided, and a natural dialogue that reads the atmosphere can be realized. The robot 100 performs a reaction (such as a backchannel) according to the directionality and the degree (strength) of the mandala in the emotion map 300. Note that the detection frequency (sampling rate) of the emotion engine is not limited to 100 ms, and may be changed according to the situation (e.g., when playing sports), the age of the user, etc.

(2) The directionality of emotions and the strength of their intensity may be preset in reference to the emotion map 300, and the movement of the interjections and the strength of the interjections may be set. For example, if the robot 100 feels a sense of stability or security, the robot 100 may nod and continue listening. If the robot 100 feels anxious, confused, or suspicious, the robot 100 may tilt its head or stop shaking its head.

These emotions are distributed in the three o'clock direction on emotion map 300, and usually fluctuate between relief and anxiety. In the right half of emotion map 300, situational awareness takes precedence over internal sensations, resulting in a sense of calm.

(3) If the robot 100 feels good after being praised, the filler "ah" may be inserted before the line, and if the robot 100 feels hurt after receiving harsh words, the filler "ugh!" may be inserted before the line. Also, a physical reaction such as the robot 100 crouching down while saying "ugh!" may be included. These emotions are distributed around 9 o'clock on the emotion map 300.

(4) In the left half of the emotion map 300, internal sensations (reactions) are more important than situational awareness. This can give the impression that the person is reacting unconsciously.

When the robot 100 feels a favorable feeling in its situational awareness while also feeling an internal sensation (reaction) of a sense of satisfaction, the robot 100 may nod deeply while looking at the other person, or may say "uh-huh." In this way, the robot 100 may generate a behavior that shows a balanced favorable feeling toward the other person, that is, acceptance and tolerance toward the other person. Such emotions are distributed around 12 o'clock on the emotion map 300.

Conversely, even when the robot 100 is aware of a situation while experiencing an internal sensation (reaction) of discomfort, the robot 100 may shake its head when it feels disgust, or turn the eye LEDs red and glare at the other person when it feels hatred. These types of emotions are distributed around the 6 o'clock position on the emotion map 300.

(5) The inside of emotion map 300 represents what is going on inside one's mind, while the outside of emotion map 300 represents behavior, so the further out on emotion map 300 you go, the more visible the emotions become (the more they are expressed in behavior).

(6) When listening to someone with a sense of relief, which is distributed around the 3 o'clock area of the emotion map 300, the robot 100 may lightly nod its head and say "hmm," but when it comes to love, which is distributed around 12 o'clock, it may nod vigorously, nodding its head deeply.

The emotion determination unit 232 inputs the information analyzed by the sensor module unit 210 and the recognized state of the user 10 into a pre-trained neural network, obtains emotion values indicating each emotion shown in the emotion map 300, and determines the emotion of the user 10. This neural network is pre-trained based on multiple learning data that are combinations of the information analyzed by the sensor module unit 210 and the recognized state of the user 10, and emotion values indicating each emotion shown in the emotion map 300. In addition, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Figure 6. Figure 6 shows an example in which multiple emotions, such as "peace of mind," "calm," and "reassuring," have similar emotion values.

Furthermore, the emotion determination unit 232 may determine the emotion of the robot 100 according to a specific mapping. Specifically, the emotion determination unit 232 inputs the information analyzed by the sensor module unit 210, the state of the user 10 recognized by the user state recognition unit 230, and the state of the robot 100 into a pre-trained neural network, obtains emotion values indicating each emotion shown in the emotion map 300, and determines the emotion of the robot 100. This neural network is pre-trained based on multiple learning data that are combinations of the information analyzed by the sensor module unit 210, the recognized state of the user 10, and the state of the robot 100, and emotion values indicating each emotion shown in the emotion map 300. For example, the neural network is trained based on learning data that indicates that when the robot 100 is recognized as being stroked by the user 10 from the output of a touch sensor (not shown), the emotional value becomes "happy" at "3," and that when the robot 100 is recognized as being hit by the user 10 from the output of an acceleration sensor (not shown), the emotional value becomes "anger" at "3." Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 6.

The behavior decision unit 236 generates the robot's behavior by adding fixed sentences to ask about the robot's behavior corresponding to the user's behavior to the text representing the user's behavior, the user's emotions, and the robot's emotions, and inputting the text into the dialogue function.

For example, the behavior determination unit 236 obtains text representing the state of the robot 100 from the emotion of the robot 100 determined by the emotion determination unit 232, using an emotion table such as that shown in Table 1. Here, in the emotion table, an index number is assigned to each emotion value for each type of emotion, and text representing the state of the robot 100 is stored for each index number.

When the emotion of the robot 100 determined by the emotion determination unit 232 corresponds to index number "2", the text "very happy state" is obtained. Note that when the emotion of the robot 100 corresponds to multiple index numbers, multiple pieces of text representing the state of the robot 100 are obtained.

In addition, an emotion table as shown in Table 2 is prepared for the emotions of the user 10.
In this case, if the user's action is speaking "***", the robot 100's emotion is index number "2", and the user's emotion is index number "3",
"The robot is in a very happy state. The user is in a normal happy state. The user says "***". As the robot, how would you respond?"
The above is input to the sentence generation model to obtain the action content of the robot. The action decision unit 236 decides the action of the robot from the action content.

In this way, the robot 100 can change its behavior according to the index number that corresponds to the robot's emotions, so that the user gets the impression that the robot has a heart, and is encouraged to take actions such as talking to the robot.

Furthermore, the behavior decision unit 236 may generate the robot's behavior content by adding not only text representing the user's behavior, the user's emotions, and the robot's emotions, but also text representing the contents of the history data 222, adding a fixed sentence for asking about the robot's behavior content corresponding to the user's behavior, and inputting the result into a sentence generation model with a dialogue function. This allows the robot 100 to change its behavior according to the history data representing the user's emotions and behavior, so that the user has the impression that the robot has a personality, and is encouraged to take actions such as talking to the robot. The history data may also further include the robot's emotions and actions.

The robot 100 may be mounted on a stuffed toy, or may be applied to a control device connected wirelessly or by wire to a control target device (speaker or camera) mounted on the stuffed toy.

In the above explanation, an example is given of the case where the behavior control system is applied to the robot 100, but the present invention is not limited to this aspect. FIG. 7 is a functional block diagram of an agent system 50 configured using some or all of the functions of the behavior control system. The agent system 50 is a computer system that performs a series of actions in accordance with the intentions of the user 60 through dialogue with the user 60. The dialogue with the user 60 can be carried out by voice or text.

The agent system 50 may be installed in, for example, a robot, a doll, a stuffed animal, a pendant, a smart watch, a smartphone, a smart speaker, earphones, a personal computer, etc. The agent system 50 may also be implemented in a web server and used via a web browser running on a communication terminal such as a smartphone owned by the user.

The agent system 50 plays a role of, for example, a butler, secretary, teacher, partner, friend, lover, or teacher acting for the user 60. The agent system 50 not only converses with the user 60, but also provides advice, guides the user to a destination, or makes recommendations based on the user's preferences. The agent system 50 also makes reservations, orders, or makes payments to the service provider 70.

The agent system 50 is equipped with an emotion engine 53, which determines the emotions of the user 60 and the agent's own emotions, and acts on behalf of the user 60 while taking into account the emotions of the user 60 and the agent. Here, the agent is an agent that runs on software. In other words, the agent system 50 understands the emotions of the user 60, reads the mood, and provides heartfelt support, assistance, advice, and services. The agent system 50 also listens to the worries of the user 60, comforts, encourages, and cheers up the user. The agent system 50 also plays with the user 60, draws picture diaries, and helps the user reminisce about the past. The agent system 50 acts in a way that increases the user 60's sense of happiness.

The agent system 50 has a dialogue processing unit 51, a character setting unit 52, an emotion engine 53, a dialogue history storage unit 54, a sentence generation model 55, a command acquisition unit 56, and RPA (Robotic Process Automation) 57.

The dialogue processing unit 51 includes a behavior decision unit 236 that performs processing related to speech, and a behavior control unit 250. The dialogue processing unit 51 generates the content of the agent's speech to converse with the user 60, and outputs this as at least one of voice and text.

The character setting unit 52 sets the character of the agent (corresponding to the agent 52A shown in FIG. 9) when the agent system 50 converses with the user 60 based on the designation from the user 60. That is, the speech content output from the dialogue processing unit 51 is output through the agent having the set character. For example, it is possible to set real celebrities or famous people such as actors, entertainers, idols, and athletes as characters. It is also possible to set fictional characters that appear in comics, movies, or animations. For example, it is possible to set "Princess Anne" played by "Audrey Hepburn" who appears in the movie "Roman Holiday" as the agent character. If the character of the agent is known, the voice, speech, tone, and personality of the character are known, so the user 60 only needs to designate the character of his/her choice, and the prompt setting in the character setting unit 52 is automatically performed. The voice, speech, tone, and personality of the set character are reflected in the dialogue with the user 60. That is, the dialogue processor 51 synthesizes a voice according to the character set by the character setting unit 52, and outputs the agent's speech using the synthesized voice. This allows the user 60 to feel as if he or she is conversing with a character of his or her choice (e.g., a favorite actor) himself or herself.

When the agent system 50 is mounted on a device with a display, such as a smartphone, an icon, still image, or video of the agent having a character set by the character setting unit 52 may be displayed on the display. The image of the agent is generated using image synthesis technology, such as 3D rendering. In the agent system 50, a dialogue with the user 60 may be conducted while the image of the agent makes gestures according to the emotions of the user 60, the emotions of the agent, and the content of the agent's speech. Note that when engaging in a dialogue with the user 60, the agent system 50 may output only audio without outputting an image.

The emotion engine 53 includes an emotion determination unit 232 and determines an emotion value indicating the emotion of the user 60 and an emotion value of the agent itself. The emotion value of the agent itself is reflected in the emotion of the set character. When the agent system 50 converses with the user 60, not only the emotion of the user 60 but also the emotion of the character is reflected in the dialogue. In other words, the dialogue processing unit 51 outputs the speech content in a manner according to the emotion determined by the emotion engine 53.

The agent's emotions are also reflected when the agent system 50 behaves toward the user 60. For example, when the user 60 requests the agent system 50 to take a photo, whether the agent system 50 will take a photo in response to the user's request is determined by the degree of "sadness" the agent is feeling. If the agent is feeling positive emotions, it will engage in friendly dialogue or behavior toward the user 60, and if the agent is feeling negative emotions, it will engage in hostile dialogue or behavior toward the user 60.

The dialogue history storage unit 54 is a storage medium for storing the history of the dialogue between the user 60 and the agent system 50. The dialogue history storage unit 54 may be realized by the history data 222 of the storage unit 220, or may be realized by an external cloud storage. When the agent system 50 dialogues with the user 60 or takes an action toward the user 60, the content of the dialogue or the action is determined by taking into account the content of the dialogue history stored in the dialogue history storage unit 54. For example, the agent system 50 grasps the hobbies and preferences of the user 60 based on the dialogue history stored in the dialogue history storage unit 54. The agent system 50 generates dialogue content that matches the hobbies and preferences of the user 60 or provides recommendations. The dialogue processing unit 51 generates utterance content based on the dialogue history stored in the dialogue history storage unit 54. The dialogue history storage unit 54 stores personal information of the user 60, such as the name, address, telephone number, and credit card number, acquired through dialogue with the user 60. Here, the agent may proactively ask the user 60 whether or not to register personal information, such as "Would you like to register your credit card number?", and the personal information may be stored in the dialogue history storage unit 54 depending on the user 60's response.

The sentence generation model 55 generates sentences that are responses to input text or voice. The sentence generation model 55 may be interpreted as algorithms and calculations for automatic dialogue processing using characters. The sentence generation model is publicly known as disclosed in, for example, JP 2018-081444 A and chatGPT (Internet search <URL: https://openai.com/blog/chatgpt>), so a detailed description thereof will be omitted. Such a sentence generation model is composed of a large language model (LLM: Large Language Model).

The dialogue processing unit 51 generates the speech content based on the sentences generated by the sentence generation model 55. Specifically, the dialogue processing unit 51 inputs the text or voice input by the user 60, the emotions of both the user 60 and the agent identified by the emotion engine 53, and the conversation history stored in the dialogue history storage unit 54 to the sentence generation model 55 to generate the agent's speech content. At this time, the dialogue processing unit 51 may further input the personality of the character set by the character setting unit 52 to the sentence generation model 55 to generate the agent's speech content. In the agent system 50, the sentence generation model 55 is not located on the front end side that is the touch point with the user 60, but is used merely as a tool for the agent system 50.

The command acquisition unit 56 is configured by the speech understanding unit 212, and acquires commands for the agent from the voice or text uttered by the user 60 through dialogue with the user 60. The commands include the content of the actions that the agent system 50 should execute, such as, for example, searching for information, making a reservation at a store, arranging tickets, purchasing a product or service, paying for it, getting route guidance to a destination, and providing recommendations.

The RPA 57 performs an action according to the command acquired by the command acquisition unit 56. The RPA 57 performs an action related to the use of the service provider 70, such as information search, store reservation, ticket arrangement, purchase of goods and services, payment, etc. The RPA 57 is an example of an "action execution unit" in the present invention.

The RPA 57 reads out from the dialogue history storage unit 54 the personal information of the user 60 required to execute actions related to the use of the service provider 70, and uses it. For example, when the agent system 50 purchases a product at the request of the user 60, it reads out and uses the personal information of the user 60, such as the name, address, telephone number, and credit card number, stored in the dialogue history storage unit 54. It is unkind to require the user 60 to input personal information in the initial settings, and it is unpleasant for the user. In the agent system 50 according to this embodiment, instead of requiring the user 60 to input personal information in the initial settings, the personal information acquired through the dialogue with the user 60 is stored, and is read out and used as necessary. This makes it possible to avoid making the user 60 feel uncomfortable, and improves user convenience.

The agent system 50 executes the dialogue process through the following steps 1 to 6.
(Step 1) The agent system 50 sets an agent character. Specifically, the character setting unit 52 sets an agent character when the agent system 50 converses with the user 60, based on a designation from the user 60.

(Step 2) The agent system 50 acquires the state of the user 10, including the voice or text input by the user 10, the emotional value of the user 10, the emotional value of the robot 100, and the history data 222. Specifically, the agent system 50 performs the same processes as steps S100 to S103 described above, and acquires the state of the user 10, including the voice or text input by the user 10, the emotional value of the user 10, the emotional value of the robot 100, and the history data 222.

(Step 3) The agent system 50 determines the content of the agent's utterance. Specifically, the dialogue processing unit 51 inputs the text or voice input by the user 60, the emotions of both the user 60 and the character specified by the emotion engine 53, and the conversation history stored in the dialogue history storage unit 54 to the sentence generation model 55, and generates the content of the agent's utterance.
For example, a fixed sentence such as "How would you respond as an agent in this situation?" is added to the text or voice input by the user 60, the emotions of both the user 60 and the character identified by the emotion engine 53, and the text representing the conversation history stored in the dialogue history storage unit 54, and this is input into the sentence generation model 55 to obtain the content of the agent's speech.
As an example, if the text or voice input by user 60 is "Please make a reservation at a delicious Chinese restaurant nearby for tonight at 7pm," the agent's speech may be retrieved as "Understood," and "Here are some recommended restaurants: 1. AAAA. 2. BBBB. 3. CCCC. 4. DDDD."
Also, if the text or voice input by the user 60 is "Number 4, DDDD, would be good," the agent's speech content acquired is "Understood. I will make a reservation. How many seats are there?".

(Step 4) The agent system 50 outputs the agent's speech. Specifically, the dialogue processing unit 51 synthesizes a voice corresponding to the character set by the character setting unit 52, and outputs the agent's speech using the synthesized voice.

(Step 5) The agent system 50 determines whether it is time to execute the agent's command. Specifically, the dialogue processing unit 51 determines whether it is time to execute the agent's command based on the output of the sentence generation model 55. For example, if the output of the sentence generation model includes information indicating that the agent will execute a command, it determines that it is time to execute the agent's command and proceeds to step 6. On the other hand, if it is determined that it is not time to execute the agent's command, it returns to step 2 above.

(Step 6) The agent system 50 executes the command of the agent. Specifically, the command acquisition unit 56 acquires the command of the agent from the voice or text issued by the user 60 through a dialogue with the user 60. Then, the RPA 57 performs an action according to the command acquired by the command acquisition unit 56. For example, if the command is "information search", an information search is performed on a search site using a search query obtained through a dialogue with the user 60 and an API (Application Programming Interface). The dialogue processing unit 51 inputs the search results into the sentence generation model 55 to generate the utterance contents of the agent. The dialogue processing unit 51 synthesizes a voice according to the character set by the character setting unit 52, and outputs the utterance contents of the agent by the synthesized voice.
Also, if the command is "reserve a restaurant", the reservation information obtained through the dialogue with the user 60, the restaurant information, and an API (Application Programming Interface) are used to make a phone call to the restaurant by telephone software to make the reservation. At this time, the dialogue processing unit 51 uses a sentence generation model with a dialogue function to obtain the agent's utterance in response to the voice input from the other party. The dialogue processing unit 51 then inputs the result of the restaurant reservation (whether the reservation was successful or not) to the sentence generation model 55 to generate the agent's utterance. The dialogue processing unit 51 synthesizes a voice according to the character set by the character setting unit 52, and outputs the agent's utterance using the synthesized voice. Then, the process returns to step 2.

In step 6, the results of the actions taken by the agent (e.g., making a restaurant reservation) are also stored in the dialogue history storage unit 54. The results of the actions taken by the agent stored in the dialogue history storage unit 54 are used by the agent system 50 to understand the hobbies or preferences of the user 60. For example, if the same restaurant has been reserved multiple times, the agent system 50 may recognize that the user 60 likes that restaurant, and may use the reservation details, such as the reserved time period, or the course content or price, as a criterion for choosing a restaurant the next time the reservation is made.

In this way, the agent system 50 executes dialogue processing and can take action related to the use of the service provider 70 as necessary. While the user is sleeping, the agent system 50 may search for news of high interest to the user based on the user's preferences acquired in advance, and when the user wakes up, the agent system 50 may deliver the news to the user. For example, the agent may say, "Looks like the Yankees won the game yesterday. Let's go to the baseball stadium tonight to cheer them on." If the user then says, "I'll have to ask my dad," the dad may say, "I don't know if we can get tickets." The agent may then say, "I'll check if we can get tickets," and from the dialogue with the user, hear seat requests and the like, and secure the tickets.

Figures 8 and 9 are diagrams showing an example of the operation of the agent system 50. Figure 8 illustrates an example of the agent system 50 making a restaurant reservation through dialogue with the user 60. The agent system 50 is able to ascertain the preferences of the user 60 based on the dialogue history with the user 60, provide a recommended list of restaurants that match the preferences of the user 60, and make a reservation at the selected restaurant.

On the other hand, FIG. 9 illustrates an example in which the agent system 50 accesses a mail order site through a dialogue with the user 60 to purchase a product. Based on the dialogue history with the user 60, the agent system 50 can estimate the remaining amount of beverages in the user 60's stock, and propose and execute the purchase of the beverage to the user 60. The agent system 50 can also understand the user's preferences based on the past dialogue history with the user 60, and recommend snacks that the user likes. In this way, the agent system 50 supports the user 60's daily life by communicating with the user 60 as a butler-like agent and performing various actions such as making restaurant reservations or purchasing and paying for products.

The agent system 50 described above can be applied to smart glasses 72. FIG. 10 is a block diagram showing an example of the hardware configuration of smart glasses 72. Smart glasses 72 are glasses-type smart devices, and are worn by a user 60 in the same manner as regular glasses. Smart glasses 72 include a control device 74, a display 76, a touch panel 78, a speaker 80, a group of sensors 82, a microphone 84, a camera 86, and a communication I/F 88. Smart glasses 72 are an example of an "electronic device" and a "wearable terminal" in the present invention.

The control device 74 is a device that controls the entire smart glasses 72, and is composed of, for example, a processor, memory, and storage (not shown). The display 76 displays various information to the user 60. The display 76 is, for example, a liquid crystal display. The display 76 is provided, for example, in the lens portion of the smart glasses 72, and the display contents are visible to the user 60. The touch panel 78 accepts input from the user 60. The speaker 80 outputs audio indicating various information to the user 60.

The sensor group 82 detects the state of the user 60. The sensor group 82 is configured to include a plurality of sensors. For example, the sensor group 82 includes an acceleration sensor 82A, a temperature sensor 82B, and a heart rate sensor 82C. Note that these sensors are merely examples, and it goes without saying that other sensors may be installed to detect the state of the user 60.

The microphone 84 captures the voice emitted by the user 60 or the environmental sounds around the smart glasses 72. The camera 86 is capable of capturing images of the surroundings of the smart glasses 72. The camera 86 is also capable of capturing images of the face of the user 60. The camera 86 is, for example, a CCD camera. The communication I/F 88 controls communication between the smart glasses 72 and the outside. The control device 74, the display 76, the touch panel 78, the speaker 80, the sensor group 82, the microphone 84, the camera 86, and the communication I/F 88 are connected to a bus 90.

FIG. 11 is a diagram showing an example of how the agent system 50 is used by the smart glasses 72. The smart glasses 72 provide various services to the user 60 using the agent system 50. For example, when the user 60 operates the smart glasses 72 (e.g., by voice input into a microphone or by tapping a touch panel with a finger), the smart glasses 72 start using the agent system 50. Here, using the agent system 50 includes a case where the control device 74 has a function similar to that of the agent system 50 and uses that function, and also includes a case where the smart glasses 72 communicate with an external device (e.g., a server) via the communication I/F 88 to use the agent system 50 stored outside the smart glasses 72.

When the user 60 operates the smart glasses 72, a touch point is created between the agent system 50 and the user 60. In other words, the agent system 50 starts providing a service. As described above, in the agent system 50, the character setting unit 52 sets the character of the agent 52A (for example, the character of Audrey Hepburn).

As described above, the emotion engine 53 includes an emotion determination unit 232, and determines an emotion value indicating the emotion of the user 60 and an emotion value of the agent itself. Here, the emotion value indicating the emotion of the user 60 may be estimated from various sensors included in the sensor group 82 mounted on the smart glasses 72. For example, when the heart rate of the user 60 detected by the heart rate sensor 82C mounted on the smart glasses 72 is increasing, emotion values such as "anxiety" and "fear" are estimated to be large. The heart rate sensor 82C is an example of an "acquisition unit" in the present invention.

In addition, when the temperature sensor 82B measures the user's body temperature and, for example, the result is higher than the average body temperature, an emotional value such as "pain" or "distress" is estimated to be high. In addition, when the acceleration sensor 82A detects that the user 60 is playing some kind of sport, an emotional value such as "fun" is estimated.

Also, for example, the emotion value of the user 60 (e.g., the emotion value of "sad") may be estimated based on the facial expression (e.g., a sad expression) of the user 60 captured by the camera 86 mounted on the smart glasses 72. In this case, the camera 86 is an example of the "acquisition unit" in the present invention.

Also, for example, the emotion value of the user 60 may be estimated from the voice of the user 60 or the content of the speech acquired by the microphone 84 mounted on the smart glasses 72. For example, if the user 60 is raising his/her voice, an emotion value such as "anger" is estimated. In this case, the microphone 84 is an example of the "acquisition unit" in the present invention.

When the emotion value estimated by the emotion engine 53 becomes higher than a predetermined value, the agent system 50 causes the smart glasses 72 to acquire information about the surrounding situation. Specifically, for example, the camera mounted on the smart glasses 72 captures an image or video showing the surrounding situation of the user 60 (for example, people or objects in the vicinity). In addition, the microphone mounted on the smart glasses 72 records the surrounding environmental sound. Other information about the surrounding situation includes date, time, location information, or information indicating the weather. The agent system 50 acquires information about the surrounding situation when the emotion value becomes high from the smart glasses 72. The information about the surrounding situation is stored in the surrounding situation storage unit 54A together with the emotion value. The surrounding situation storage unit 54A is a storage medium for storing information about the surrounding situation acquired by the agent system 50. The surrounding situation storage unit 54A may be realized by the history data 222 of the storage unit 220, similar to the dialogue history storage unit 54, or may be realized by an external cloud storage. In this way, the surrounding situation obtained by the smart glasses 72 is stored in the surrounding situation storage unit 54A as a so-called life log in association with the emotion value of the user 60 at that time.

In the agent system 50, information indicating the surrounding situation is stored in the surrounding situation storage unit 54A in association with an emotional value. This allows the agent system 50 to grasp personal information such as the user 60's hobbies, preferences, or personality. For example, if an image showing a baseball game is associated with an emotional value such as "joy" or "fun," the agent system 50 will understand that the user 60's hobby is watching baseball games and that the user's favorite team or player is based on the information stored in the surrounding situation storage unit 54A.

When the agent system 50 converses with the user 60 or takes an action toward the user 60, the agent system 50 determines the content of the dialogue or the action by taking into account the content of the surrounding circumstances stored in the surrounding circumstances storage unit 54A. Of course, the dialogue content or the action content may be determined by taking into account the dialogue history stored in the dialogue history storage unit 54 as described above, in addition to the surrounding circumstances.

As described above, the dialogue processing unit 51 generates the speech content based on the sentences generated by the sentence generation model 55. Specifically, the dialogue processing unit 51 inputs the text or voice input by the user 60, the emotions of both the user 60 and the agent identified by the emotion engine 53, the conversation history stored in the dialogue history storage unit 54, and the agent's personality, etc., into the sentence generation model 55 to generate the agent's speech content. Furthermore, the dialogue processing unit 51 inputs the surrounding circumstances stored in the surrounding circumstances storage unit 54A into the sentence generation model 55 to generate the agent's speech content.

The generated speech content is output to the user 60, for example, as audio from the speaker 80 mounted on the smart glasses 72. In this case, a synthetic voice corresponding to the character of the agent is used as the voice. The dialogue processing unit 51 generates a synthetic voice by reproducing the voice quality of the agent character (e.g., Audrey Hepburn), or generates a synthetic voice corresponding to the emotion of the character (e.g., a voice with a stronger tone in the case of the emotion of "anger"). The speech content may be displayed on the display 76 instead of or in addition to the audio output. The speaker 80 and the display 76 are examples of the "output unit" in this invention.

The RPA 57 executes an operation according to a command (e.g., an agent command obtained from a voice or text issued by the user 60 through a dialogue with the user 60). The RPA 57 performs actions related to the use of the service provider 70, such as information search, store reservation, ticket arrangement, purchase of goods and services, payment, route guidance, translation, etc.

As another example, the RPA 57 executes an operation to transmit the contents of voice input by the user 60 (e.g., a child) through dialogue with an agent to a destination (e.g., a parent). Examples of transmission means include message application software, chat application software, or email application software.

When an operation is executed by the RPA 57, for example, a sound indicating that execution of the operation has been completed is output from the speaker 80 mounted on the smart glasses 72. For example, a sound such as "Your restaurant reservation has been completed" is output to the user 60. Also, for example, if the restaurant is fully booked, a sound such as "We were unable to make a reservation. What would you like to do?" is output to the user 60.

As described above, the smart glasses 72 provide various services to the user 60 by utilizing the agent system 50. In addition, since the smart glasses 72 are worn by the user 60, it is possible to use the agent system 50 in various situations, such as at home, at work, or when out and about.

In addition, because the smart glasses 72 are worn by the user 60, they are suitable for collecting the so-called life log of the user 60. Specifically, the emotional value of the user 60 is estimated based on the detection results of various sensors mounted on the smart glasses 72 or the recording results of the camera 86, etc. Therefore, the emotional value of the user 60 can be collected in various situations, and the agent system 50 can provide services or speech content appropriate to the emotions of the user 60.

In addition, the smart glasses 72 obtain the surrounding conditions of the user 60 through the camera 86, microphone 84, etc. These surrounding conditions are associated with the emotion values of the user 60. This makes it possible to estimate what emotions the user 60 felt in what situations. As a result, the accuracy with which the agent system 50 grasps the hobbies and preferences of the user 60 can be improved. By accurately grasping the hobbies and preferences of the user 60 in the agent system 50, the agent system 50 can provide services or speech content that are suited to the hobbies and preferences of the user 60.

The agent system 50 can also be applied to a smart pendant 92. FIG. 12 is a block diagram showing an example of the hardware configuration of the smart pendant 92. The smart pendant 92 is a pendant-type smart device, and is worn by the user 60 in the same manner as a general pendant. The smart pendant 92 includes a control device 93, a speaker 94, a microphone 95, and a communication I/F 96. The smart pendant 92 is an example of the "electronic device" and "wearable terminal" of the present invention.

The control device 93 is a device that controls the entire smart pendant 92, and is composed of, for example, a processor, memory, and storage (not shown). The speaker 94 outputs sound indicating various information to the user 60. The speaker 94 is, for example, a speaker that can output sound with directionality (i.e., a directional speaker). The speaker 94 is set so that it has directionality toward the ears of the user 60. This prevents the sound from reaching people other than the user 60. The speaker 94 is an example of an "output unit" in the present invention.

The microphone 95 acquires the voice uttered by the user 60 or the environmental sounds around the smart pendant 92. The smart pendant 92 is worn by hanging it from the neck of the user 60. Therefore, the smart pendant 92 is located relatively close to the mouth of the user 60 while it is worn. This makes it easy to acquire the voice uttered by the user 60. The microphone 95 is an example of an "acquisition unit" in the present invention. The communication I/F 96 manages communication between the smart pendant 92 and the outside. The control device 93, the speaker 94, the microphone 95, and the communication I/F 96 are connected to a bus 97.

The agent system 50 can also be used in the smart pendant 92. That is, the services provided by using the agent system 50 in the smart glasses 72 described above (see FIG. 11) are also provided in the smart pendant 92. For example, the emotional values of the user 60 and the agent are estimated through dialogue with an agent with a set character, and the agent's speech or the content of the service provided changes depending on the emotional value. In addition, for example, the situation around the user 60 and the emotional value at that time are recorded as a life log, and are reflected in the estimation of the user 60's emotional value or the content of the service provided.

The smart pendant 92 may also be provided with a sensor group (corresponding to the sensor group 82 in the smart glasses 72) in the same manner as the smart glasses 72. This allows information indicating the physical condition of the user 60 or the surrounding situation to be detected, and allows the agent system 50 to estimate an emotional value and record the surrounding situation.

As described above, the smart pendant 92 can achieve the same effect as the smart glasses 72 described above. Furthermore, the smart pendant 92 is lighter and easier to carry than a stuffed toy, a smart speaker, a smartphone, or smart glasses. Furthermore, compared to other smart terminals such as a smartphone or smart glasses, the smart pendant 92 is lighter and more portable since it is worn on a daily basis. Therefore, the agent system 50 can be used in various situations, such as at home, at work, or outside. Furthermore, the smart pendant 92 is more suitable for collecting the life log of the user 60, and therefore can collect the emotional values of the user 60 in various situations, and the agent system 50 can provide services or speech content that are appropriate for the emotions of the user 60.

Below is a description of an example of a to-do management application that uses an agent system to manage the behavior history of a user-specified behavior history target.

The user and the behavior history target have a predetermined relationship. In this embodiment, the user 10 is the manager (parent) of the robots 100, 101, and 102 (hereinafter collectively referred to as robot 100) shown in FIG. 1, while the behavior history target is set as the child 400 of the user 10 (see FIG. 13), and a parent-child relationship is assumed.

The execution program of the ToDo management application in this embodiment is executed by the functions of the CPU (each functional component shown in FIG. 2). As described above, the functional components include a sensor unit 200, a sensor module unit 210, a storage unit 220, a user state recognition unit 230, an emotion determination unit 232, a behavior recognition unit 234, a behavior determination unit 236, a memory control unit 238, a behavior control unit 250, a control target 252, and a communication processing unit 280, and the ToDo management application is executed by the cooperation of each functional component (see FIG. 2).

In the to-do management application, the robot 100 is controlled to execute the following (operation 1) to (operation 5) in response to a command from the user 10 (parent) to monitor the behavior of the behavior history target (child 400).

(Operation 1) The robot 100 sequentially recognizes the behavior of the behavior history target (child 400) and stores the behavior history.
(Operation 2) A specific action is selected from a pre-registered to-do list and a confirmation message is sent to the robot 100 from the communication terminal (smartphone or mobile phone) of the user 10 (parent) using SNS as an instruction to determine whether the specific action has been completed or not (for example, "Did you do your homework?"). Note that the specific action is not limited to homework, and can be any action that has been pre-registered in the to-do list, such as tidying up, taking a nap, feeding a pet, etc. If you want to check a specific action that has not been registered in the to-do list, you can add it. In this case, if there is an action history for the additionally registered specific action, it can be handled.
(Operation 3) The robot 100 judges from the behavior history of the child 400 whether or not the child 400 has done his/her homework.
(Action 4 "Action 4-1 or Action 4-2")
Operation 4-1: If the child 400 is doing his/her homework (see the behavioral history in FIG. 13A), the prompt "How should I praise my child if he/she is doing his/her homework voluntarily?" is input to the sentence generation model 55 to instruct the creation of a sentence regarding how to encourage him/her (words of praise).
Operation 4-2: If the child 400 is not doing his/her homework (see the behavioral history in FIG. 3B), the prompt "How can I encourage my child to do his/her homework?" is input to the sentence generation model 55, and a sentence regarding how to encourage the child 400 (words of encouragement) is generated.
(Operation 5) Words of praise (in the case of Operation 4-1) or words of encouragement (in the case of Operation 4-2) are output to the child 400 by voice from a speaker mounted on the robot 100 or from connected earphones.

Figure 13 is a front view of a group of images 402A and 402B taken in chronological order for determining the history of a specific event (behavior of a specified behavior history target) by a camera (for example, the 2D camera 203, which is one of the sensor units 200 mounted on the robot 100 shown in Figure 2) managed and controlled by the agent system.

Figure 13 shows a group of images extracted when a user 10 gives an instruction regarding the behavioral history of whether or not the behavioral history target (child 400) has done their homework.

Figure 13 (A) shows an example of a group of images when child 400 has done his/her homework, and Figure 13 (B) shows an example of a group of images when child 400 has not done his/her homework. In reality, one or the other of the image groups will exist during the same time period.

The camera is not limited to the 2D camera 203 mounted on the robot 100, and the robot 100 may acquire images taken by cameras installed in each room indoors via communication. This makes it possible for the robot 100 to acquire images for the behavior history even if it does not follow the behavior of the child 400.

As shown in FIG. 13(A), when checking the group of images taken when doing homework in chronological order, in the early behavioral history, child 400 is lying down and operating smartphone 404, in the middle behavioral history, child 400 is watching television 406, but in the final behavioral history, child 400 is seated at desk 408. Taking all these together, it can be seen that child 400 is studying (doing homework).

In this case, which corresponds to (action 4-1) above, the robot 100 inputs to the sentence generation model 55, "How should I praise my child if he or she voluntarily does his or her homework?" In response to this input, the sentence generation model 55 acquires the appropriate words of praise.

As shown in FIG. 13B, when checking the group of images taken when not doing homework in chronological order, in the early behavioral history, child 400 is lying down and operating smartphone 404, in the middle behavioral history, child 400 is sitting at desk 408 but dozing off, and even in the final behavioral history, child 400 is seen leaving desk 408 with soccer ball 410 in hand, and taking all of this into account, it can be confirmed that child 400 is not doing his homework.

In this case, which corresponds to (action 4-2) above, the robot 100 inputs to the sentence generation model 55, "How should I encourage my child to do their homework?" In response to this input, the sentence generation model 55 acquires the way to encourage the child (words of encouragement).

Figure 14 is a control flowchart showing the flow of acquiring behavior history in the processing of a to-do management application executed by the robot's control device.

In step 420, it is determined whether or not an instruction to start the behavior history has been received. The instruction to start the behavior history may be synchronized with the start of the robot 100, may be a time period set by a timer or the like, or may be an instruction from the user 10. In the case of this embodiment (determining the behavior history of the child 400), the start time may be when the parent, who is the user 10, goes out.

If the determination at step 420 is negative, this routine ends. If the determination at step 420 is positive, the process proceeds to step 422, where information is acquired to identify the behavioral history subject designated by the user 10 (in this embodiment, the child 400). Examples of the identifying information include features used for face recognition, appearance features, and voice features. Note that the behavioral history subject may be multiple people (siblings, etc.).

In the next step 424, shooting is started. In the next step 426, the captured image is searched for the behavioral history target (child 400), and then the process proceeds to step 428, where a tracking shooting process is performed for the searched behavioral history target (child 400). The tracking shooting process involves time lapse shooting (frame-by-frame shooting), and if there are multiple behavioral history targets, the images are classified by behavioral history target, and the captured images are stored in chronological order. Time lapse shooting may be for still images or videos.

In the next step 430, it is determined whether or not an instruction to end the behavior history has been received. The instruction to end the behavior history may be synchronized with the end of the activation of the robot 100, or may be a time period set by a timer or the like, or an instruction from the user 10. In the case of this embodiment (determining the behavior history of the child 400), the activation end time may be when the parent, who is the user 10, returns home from outside.

If the result of step 430 is negative, the process returns to step 426 to continue the behavioral history, and the above steps are repeated. If the result of step 430 is positive, the process proceeds to step 432, where image capture ends, and the routine ends.

In other words, the behavior history (tracking photography process) will continue until an instruction to end the behavior history is given.

Figure 15 is a control flowchart showing the flow of an interrupt routine that is executed when a request for behavior history determination is made during execution of the behavior history in Figure 14 (during tracking photography processing).

In this embodiment, the behavior history determination request is received by the robot 100 via SNS from the user 10 (parent) who is out, asking, "Did you do your homework?" When the robot 100 receives this information, an interrupt routine for requesting behavior history determination is started.

In step 440, the behavioral history target (child 400) to be judged is identified. For example, if there are multiple behavioral history targets, identification information such as "eldest son" or "○○-kun" is required.

In the next step 442, the time-series image data of the identified behavioral history subject (child 400) is read out. That is, in this embodiment, either the time-series image of FIG. 13(A) or FIG. 13(B) is actually stored, and either the time-series image data is read out.

In the next step 444, the result of the requested judgment (a judgment of whether a specific action has been accomplished or not) is analyzed. Here, a positive judgment (homework accomplished) or a negative judgment (homework not accomplished) is made in response to the request "Did you do your homework?".

When the read time-series image data is as shown in FIG. 13(A), it is possible to confirm from the time-series images of the child 400 lying down and operating the smartphone 404 (initial stage) → watching the television 406 (middle stage) → sitting at the desk 408 (end stage) that the child 400 is studying (doing his homework), so a positive judgment is made.

On the other hand, if the read time-series image data is as shown in FIG. 13(B), it is possible to confirm from the time-series images of child 400 lying down and operating smartphone 404 (initial stage) → facing desk 408 but dozing off (middle stage) → walking away from desk 408 with soccer ball 410 (end stage) that child 400 is not doing his homework, so a negative judgment is made.

The next step, 446, determines whether the result of the determination in step 444 is a positive or negative determination.

If the result is determined to be positive in step 446, the process proceeds to step 448, where the sentence "How should I praise my child if he or she is doing his or her homework voluntarily?" is input to the sentence generation model 55 (ChatGPT is an example), and the process proceeds to step 452.

If the result of the judgment in step 446 is negative, the process proceeds to step 450, where the question "How can we encourage a child to do their homework?" is input to the sentence generation model 55 (ChatGPT is an example), and the process proceeds to step 452.

In step 452, it is determined whether or not a response has been received from the sentence generation model 55 (ChatGPT as an example), and if a positive determination is made, the process proceeds to step 454, where the response received from the sentence generation model 55 (ChatGPT as an example) is output as audio from a speaker or the like, and this routine ends.

In step 454, a sentence generation model 55 (one example is ChatGPT) responds to a positive judgment (homework has been done) with an example of a response from ChatGPT, such as "Good job! There are snacks in the fridge, so have some."

On the other hand, in step 454, an example of a response from the sentence generation model 55 (ChatGPT is one example) to a negative judgment (not doing homework) is, "There are snacks in the fridge, so please eat them when you finish your homework."

As described above, in this embodiment (ToDo management application), the robot 100 equipped with an agent system acts on behalf of the user 10 (parent) who is out and determines whether the behavioral history subject (child 400) who is at home alone has done his/her homework, and queries ChatGPT about each situation of doing homework (positive) and not doing homework (negative), and receives advice (appropriate words) and can speak appropriate words to the child 400 by voice.

The electronic device is not limited to the robot 100, but may be other electronic devices capable of mounting an agent system (such as a doll, a stuffed animal, smart glasses 72 (see FIG. 10), a smart pendant 92 (see FIG. 12), a smart watch, a smartphone, a smart speaker, earphones, and a personal computer).

In addition, in this embodiment, the relationship between the user 10 and the behavioral history target is that of a parent and child (guardian and protected person), but this is not limited to a parent and child relationship, and can be applied to any relationship established between a manager (guardian) and a managed person (protected person), such as a boss and a subordinate, a master and an apprentice, an ordering party and a receiving party, an owner and a pet, etc.

Furthermore, in this embodiment, the behavior history target (child 400) is distinguished from the user 10, but in a broader sense, the behavior history target may also belong to the user 10. That is, the user 10 may designate himself/herself as a behavior history target and make it the target of the behavior history of the robot 100. Alternatively, among multiple users 10, one user 10 may designate another user 10 as a behavior history target and make it the target of the behavior history of the robot 100.

5 System, 10, 11, 12, 60 User, 20 Communication network, 100, 101, 102 Robot, 200 Sensor unit, 201 Microphone, 202 Depth sensor, 203 Camera, 204 Distance sensor, 210 Sensor module unit, 211 Voice emotion recognition unit, 212 Speech understanding unit, 213 Facial expression recognition unit, 214 Face recognition unit, 220 Storage unit, 221 Response rules, 222 History data, 230 User state recognition unit, 232 Emotion determination unit, 234 Behavior recognition unit, 236 Behavior determination unit, 238 Memory control unit, 250 Behavior control unit, 252 Control target, 280 Communication processing unit, 300 Server, 1200 Computer, 1210 Host controller, 1212 CPU, 1214 RAM, 1216 Graphic controller, 1218 Display device, 1220 I/O controller, 1222 Communication interface, 1224 Storage device, 1226 DVD drive, 1227 DVD-ROM, 1230 ROM, 1240 I/O chip, 50 Agent system, 51 Dialogue processing unit, 52 Character setting unit, 52A Agent, 53 Emotion engine, 54 Dialogue history storage unit, 54A Surrounding situation storage unit, 55 Sentence generation model, 56 Command acquisition unit, 57 RPA, 70 Service provider, 72 Smart glasses, 74 Control device, 76 Display, 78 Touch panel, 80 Speaker, 82
Sensor group, 82A acceleration sensor, 82B temperature sensor, 82C heart rate sensor, 84 microphone, 86 camera, 88 communication I/F, 90 bus, 92 smart pendant, 93 control device, 94 speaker, 95 microphone, 96 communication I/F, 97 bus

Claims (4)

An electronic device capable of using an agent system, the electronic device including: an emotion determining unit that determines an emotion of a user or an emotion of an agent; and a dialogue processing unit that determines an utterance content of the agent for dialogue with the user based on the emotion determined by the emotion determining unit,
An acquisition unit capable of acquiring information regarding the user's state;
a determination unit that determines whether a specific behavior of a behavior history target has been achieved or not based on the behavior history of the behavior history target;
an execution unit that, when a determination instruction is given from the user as to whether the specific behavior has been achieved or not, causes the agent system to generate a sentence regarding the specific behavior based on a determination result of the determination unit regarding the specific behavior;
an output unit that outputs the sentence generated in the agent system to the user as the speech content;
An electronic device comprising: A storage unit for storing action history images captured in time series by following the action of the action history target,
The electronic device according to claim 1 , wherein the determination unit determines whether the specific behavior has been achieved or not based on the behavior history image stored in the storage unit. The electronic device of claim 1, wherein a relationship is established between the user and the behavior history target, in which the user is a manager or guardian and the behavior history target is a person under management or a person under protection. the relationship between the user and the behavior history target is a relationship between a parent and a child under the parent's care,
The electronic device according to claim 1 , wherein the specific action is selected from actions registered in advance as a to-do list for the child.